检索结果-内蒙古大学图书馆

IEEE International Conference on Mechatronics, robotics and Automation (ICMRA)

作者： Wanghui Wu Tao Lu Jiaming Wang Pan Tang Fangqun Gao Hubei Key Laboratory of Intelligent Robot Wuhan Institute of Technology Wuhan China Wuhan Institute of Technology Wuhan China State Key Laboratory of Power Grid Environmental Protection China Electric Power Research Institute Wuhan China

ISBN: (数字)9798350352474

ISBN: (纸本)9798350352481

Due to the variability of video length and action duration, the temporal action detection task faces the problem of blurred action boundaries that are difficult to capture accurately. To alleviate this problem, this paper proposes a Frequency Attention Mechanism (FAM) that adaptively models the frequency dependencies between video signal channels, enabling the model to better understand the frequency variations in the video and to handle the complexity of different action durations, thus enhancing the sensitivity and discriminative power of the action boundaries, and still providing powerful action recognition even in long video sequences Capabilities. Through comprehensive experimental validation on a series of representative benchmark datasets (e.g. THUMOS14 and ActivityNet1.3), our approach demonstrates significant performance improvement.

关键词： Adaptation models Attention mechanisms Sensitivity Mechatronics Video sequences Benchmark testing Transformers Complexity theory robotics and automation Faces

来源：评论

学校读者我要写书评

暂无评论

A method for obtaining user requirements based on NLTK and knowledge graph 5

A method for obtaining user requirements based on NLTK and k...

引用

5th World Conference on Mechanical Engineering and intelligent Manufacturing, WCMEIM 2022

作者： Wang, Zhanfei Tan, Libin Yu, Xiaoliu Anhui University of Technology AnHui Province Key Laboratory of Special Heavy Load Robot Ma'Anshan243002 China Beijing Advanced Innovation Center for Intelligent Robots and Sy Stems Beijing Institute of Technology China

ISBN: (纸本)9781665473699

The traditional product design scheme can no longer fully meet the current user needs. To solve some problems that live in the period of small and medium batch products' design in traditional solutions, such as long cycles and a lot of differences between design direction and user needs as well as the high technical difficulty of current deep learning-assisted products. This paper proposes a rapid update design method for small batch products based on a knowledge graph, combining data mining and Python module methods. This method aims to reasonably reduce technical requirements, obtain user comments with intelligent crawler plug-ins, complete the extraction of demand information with two key modules of NLTK and Stanford CoreNlp, and realize visualization with a knowledge graph. © 2022 IEEE.

关键词： Product design

来源：评论

学校读者我要写书评

暂无评论

Three-phase Voltage PWM Rectifier Based on EID and Improved ADRC Control

Three-phase Voltage PWM Rectifier Based on EID and Improved ...

引用

Annual Conference of Industrial Electronics Society

作者： Junjie Lu Zixin Huang Wei Wang School of Electrical and Information Wuhan Institute of Technology Wuhan China Hubei Key Laboratory of Intelligent Robot Wuhan Institute of Technology Wuhan China Hubei Key Laboratory of Digital Textile Equipment Wuhan Textile University Wuhan China

ISBN: (数字)9781665464543

ISBN: (纸本)9781665464550

In high-precision occasions, three-phase voltage PWM rectifier based on conventional voltage-current dual closed-loop control suffer from current harmonics and poor interference immunity. In order to effectively alleviate the above problems, partial feedback linearisation control is introduced in the current inner loop, and equivalent input disturbance (EID) based active disturbance rejection control (ADRC) control is introduced in the voltage outer loop, and the fal function is changed to qin function to solve the jitter problem that occurs when the inflection point is not smooth. Firstly, the mathematical model of the three-phase voltage PWM rectifier in the dq coordinate system is established, and its underactuated characteristics are analysed; Then, the feedback linearisation controller is designed with current as the actuated variables, and the improved EID\ADRC controller is designed with voltage as the underactuated variable; Finally, simulation experiments are carried out by Matlab/Simulink to verify the feasibility of the proposed method.

关键词： Robust control Industrial electronics Rectifiers Interference Pulse width modulation Jitter Harmonic analysis Mathematical models Voltage control MATLAB

来源：评论

学校读者我要写书评

暂无评论

A Multi-robot 3D Point Cloud Map Merging Method Based on Overlapping Region

A Multi-Robot 3D Point Cloud Map Merging Method Based on Ove...

引用

IEEE International Conference on Mechatronics, robotics and Automation (ICMRA)

作者： Ke Xu Tao Lu Jiaming Wang Pan Tang Hubei Key Laboratory of Intelligent Robot Wuhan Institute of Technology Wuhan China Wuhan Institute of Technology Wuhan China State Key Laboratory of Power Grid Environmental Protection China Electric Power Research Institute Wuhan China

ISBN: (数字)9798350352474

ISBN: (纸本)9798350352481

In multi-robot mapping, differences in sensor capabilities across various robotic platforms can result in significant discrepancies in the generated maps. A more critical issue is the large displacement between maps, making it difficult to determine the transformation relationships between them accurately. Additionally, multi-robot SLAM often requires processing a larger number of points, leading to substantial computational resource consumption. This paper presents a two-stage alignment algorithm for merging 3D point cloud maps. The algorithm does not require any initial guesses for the transformations between local maps but instead relies on the overlapping regions of the maps to align and merge them. Initially, the original maps are segmented and sub-maps are extracted to reduce the number of points, thereby accelerating the subsequent processing efficiency. The extracted sub-maps are then globally aligned with the local maps from another robot, resulting in a rough transformation matrix. This global alignment solution is used as the initial guess for point-based fine registration, subsequently refined. In this process, we use a voxelized Generalized Iterative Closest Point fine registration algorithm to avoid expensive nearest neighbor searches, thereby increasing registration speed while maintaining accuracy. Finally, the data is merged to obtain an accurate global map. The efficiency and accuracy of the proposed 3D point cloud map merging method have been validated through experiments on public datasets.

关键词： Point cloud compression Three-dimensional displays Accuracy Simultaneous localization and mapping Mechatronics Merging Nearest neighbor methods Iterative methods

来源：评论

学校读者我要写书评

暂无评论

FIPFuse: Visible and Infrared Image Fusion Based on Frequency Information Perception

FIPFuse: Visible and Infrared Image Fusion Based on Frequenc...

引用

IEEE International Conference on Mechatronics, robotics and Automation (ICMRA)

作者： Shaokang Jiao Yanan Li Huabing Zhou School of Computer Science and Engineering Wuhan Institute of Technology Wuhan China The Key Laboratory for Crop Production and Smart Agriculture of Yunan Province Kunming China Hubei Key Laboratory of Intelligent Robot Wuhan China

ISBN: (数字)9798350352474

ISBN: (纸本)9798350352481

The fusion of visible and infrared images aims to generate fused images that has the advantages of both modalities. Traditional methods typically rely on manually designed strategies for feature extraction and fusion, resulting in increased computational complexity. The existing deep learning methods ignore the utilization of the frequency information of the source images. These methods are typically unsupervised and constrained by loss functions during the training. However, the limitations of previous loss functions have led to training that focuses excessively on the local information region of the source images, ignoring important global information. In order to solve the above problems, this paper proposes a visible and infrared image fusion method based on frequency information perception designed as FIPFuse. The frequency information perception module in FIPFuse is utilized in both the image reconstruction and image fusion stages, effectively extracting high-frequency and low-frequency information from the source images. A random structure similarity loss was proposed to train the model, with the objective of guiding the network to sufficiently focus on the source image information, thereby effectively fusing the source images. Extensive experiments on public datasets have demonstrated that FIPFuse outperforms other representative methods in both qualitative and quantitative assessments.

关键词： Training Deep learning Mechatronics Feature extraction Data mining robotics and automation Computational complexity Image fusion Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Optimized Design and Experimental Study of Shank Structure of Biped robot *

Optimized Design and Experimental Study of Shank Structure o...

引用

IEEE International Conference on robotics and Biomimetics

作者： Meijuan Qin Lingyu Kong Daming Nie Hongjian Jiang Yu Zhang Yili Fu Intelligent Robot Research Center Zhejiang Laboratory Hangzhou China Harbin Institute of Technology The National Key Laboratory of Robotics and Systems Harbin China

Lightweight design can improve the energy efficiency of biped robots, which is significant in the field of biped robot. Topology optimization has been widely used in the field of robot. However, the existing optimization is limited to the structural space based on traditional empirical design, and the potential of topology optimization is not fully utilized. Moreover, the finite element model is too simplified, which leads to a large optimization deviation. In this paper, a method of structural innovation design for the shank structure of biped robot is proposed. In the initial stage of conceptual design, the design space of optimization object is effectively maximized. Then, the load transmission characteristics of bearings are simulated by link10 element, and the topology optimization method of multiple load cases is carried out to obtain the optimized shank structure, which reduces the weight by 14.09 % compared with the existing shank. Finally, finite element extreme strength check and experiment test are both used to verify the feasibility and availability of the structure.

关键词：

来源：评论

学校读者我要写书评

暂无评论

6D Grasp Pose Detection in Cluttered Environment from a Single-view

6D Grasp Pose Detection in Cluttered Environment from a Sing...

引用

IEEE International Conference on robotics and Biomimetics

作者： Enbo Li Yili Fu Haibo Feng Zhejiang Laboratory Intelligent Robot Research Center Hangzhou China State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin China

robot grasping has always been a hot topic in the research field, but there are still a lot of problems to be solved. In this paper, we propose a general grasping method for the unknown objects in cluttered environment from a single-view. Our method is divided into three steps: sampling points selection, grasping pose sampling and grasping pose evaluation. Firstly, we generate a pixel-wise probability image based on the trained sampling affordance network from RGB images, and map the points with high probability to the 3D point cloud combined with the depth map. Then, we obtaine the candidate grasps by sampling on the proposal points, and finally we evaluate the candidate grasps through the trained grasp evaluation network. The network can capture the geometric structure represented by the point cloud information. The proposed method directly uses the original sensor data and can increases the sampling success rate.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Efficient and Robust Tightly Coupled Framework for Lidar-IMU Localization and Mapping

An Efficient and Robust Tightly Coupled Framework for Lidar-...

引用

IEEE International Conference on robotics and Biomimetics

作者： Yanwu Zhai Yili Fu Xu Li Intelligent Robot Research Center Zhejiang Laboratory Hangzhou China State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin China

In this article, we propose a framework for tightly-coupled lidar inertial odometry, which can achieve highly accuracy in real-time ego-motion estimation and map building of the robot. The estimated motion from inertial measurement unit (IMU) preintegration de-skews point clouds. Then, an initialization method based on MAP estimation is used to align the Lidar frame with the world frame and provide reliable initial values for the system. In order to make the scan matching more accurate, we track the state of each frame, and transform the feature points to the reference frame to build a local map for matching with key frames. To ensure high performance in real-time, an efficient sliding window was used to optimize the keyframes we chose. After obtaining the optimized pose of the keyframe, we further optimize the pose of the normal frame by pose constraints. In addition, loop detection is integrated into our algorithm framework to eliminate accumulated errors, making our algorithm to obtain a globally consistent estimate. The experiment results demonstrate that our method can achieve high accuracy in a variety of indoor and outdoor environments even under fast motion conditions or with insufficient features.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MorNet: Asymmetric UNet-like Network with Morphological Opening and Closing for Image Segmentation 17th

MorNet: Asymmetric UNet-like Network with Morphological Open...

引用

17th International Conference on intelligent robotics and Applications, ICIRA 2024

作者： Li, Meng Yun, Juntong Jiang, Du Tao, Bo Li, Gongfa Liu, Rong Liu, Ying Key Laboratory of Metallurgical Equipment and Control Technology of Ministry of Education Wuhan University of Science and Technology Wuhan430081 China Research Center for Biomimetic Robot and Intelligent Measurement and Control Wuhan University of Science and Technology Wuhan430081 China Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering Wuhan University of Science and Technology Wuhan430081 China Precision Manufacturing Research Institute Wuhan University of Science and Technology Wuhan430081 China School of Medicine Wuhan University of Science and Technology No. 1 Huangjia Lake University Town Wuhan430065 China School of Mechanical Engineering Hubei Engineering University Xiaogan432000 China

ISBN: (纸本)9789819607761

Image segmentation plays a crucial role in target recognition as it provides an essential prerequisite for identifying targets. However, UNet cannot acquire comprehensive information about the image, which limits its ability to effectively segment small and discrete objects. A new network structure, called MorNet, is proposed. It applies dilation and erosion operations in morphological opening and closing for connected and discrete region segmentation. MorNet effectively integrates global segmentation images, emphasizing small and discrete area segmentation and enhancing the segmentation of large continuous areas. This method enhances the understanding of the location of organs and diseased sites, enabling accurate segmentation. A side-out (SO) monitoring mechanism is introduced into the decoder to provide monitoring information for the original image and the predicted results. Compared with current UNet-like networks, our proposed method achieved the highest Dice scores (96.4635%, 94.0514%, 94.3444%) and PPV scores (94.2226%, 90.2361%, 91.5582%) for liver tumor, brain tumor, and liver segmentation tasks, respectively. The experimental results show that MorNet successfully combines the segmentation of connected and discrete regions. MorNet locates organs and lesions more accurately than current state-of-the-art medical image segmentation models. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

3D Lane Detection From Front or Surround-View Using Joint-Modeling & Matching

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on intelligent Vehicles 2024年 1-14页

作者： Zhou, Haibin Zhou, Huabing Chang, Jun Lu, Tao Ma, Jiayi Hubei Key Laboratory of Intelligent Robot Wuhan Institute of Technology Wuhan China Computer Science School Wuhan University Wuhan China Electronic Information School Wuhan University Wuhan China

3D lanes offer a more comprehensive understanding of the road surface geometry than 2D lanes, thereby providing crucial references for driving decisions and trajectory planning. While many efforts aim to improve prediction accuracy, we recognize that an efficient network can bring results closer to lane modeling. However, if the modeling data is imprecise, the results might not accurately capture the real-world scenario. Therefore, accurate lane modeling is essential to align prediction results closely with the environment. This study centers on efficient and accurate lane modeling, proposing a joint modeling approach that combines Bézier curves and interpolation methods. Furthermore, based on this lane modeling approach, we developed a Global2Local Lane Matching method with Bézier Control-Point and key-Point, which serve as a comprehensive solution that leverages hierarchical features with two mathematical models to ensure a precise match. We also introduce a novel 3D Spatial Encoder, representing an exploration of 3D surround-view lane detection research. The framework is suitable for front-view or surround-view 3D lane detection. By directly outputting the key points of lanes in 3D space, it overcomes the limitations of anchor-based methods, enabling accurate prediction of closed-loop or U-shaped lanes and effective adaptation to complex road conditions. This innovative method establishes a new benchmark in front-view 3D lane detection on the Openlane dataset and achieves competitive performance in surround-view 2D lane detection on the Argoverse2 dataset. IEEE

关键词： Interpolation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：